← Back to directory
COMPARE UP TO 4 SERVERS

Compare MCP servers

Compare scores, permissions, risks, and fit in one decision-focused table.

Dimensiondraw.io MCP ServerCreate and render live, interactive draw.io diagrams inline in chat.CompartmentEncrypted, fully offline long-term memory for AI agents
FMRS68 / 100 · C75 / 100 · B
Reliability9 / 2012 / 20
Security and permissions14 / 2016 / 20
Maintenance15 / 2014 / 20
Documentation16 / 2018 / 20
Setup experience14 / 2015 / 20
Best for
  • Users who want inline diagram previews without leaving the chat
  • Teams brainstorming architecture or process diagrams in Claude.ai or Cursor
  • Users comfortable relying on the hosted mcp.draw.io endpoint
  • Individuals or teams who prioritise privacy and offline operation and do not want data leaving the machine
  • Users who share memory across multiple MCP clients such as Claude Code, Claude Desktop, Hermes Agent, OpenClaw, Cursor, Codex and Gemini CLI
  • Scenarios that need encrypted storage, a hash-chained audit log and verifiable vault migration
  • Users who want low-latency recall, a bundled embedding model and no extra LLM calls inside the memory layer
Not for
  • Users needing local .drawio files, PNG/SVG/PDF export, or Mermaid/CSV input (use the MCP Tool Server or Assistant Plugins instead)
  • Strict data-residency environments that cannot send diagram XML to the hosted mcp.draw.io endpoint (self-hosting required)
  • MCP hosts without MCP Apps extension support, where diagrams return as text only
  • Users who need cloud multi-device sync or a hosted team memory service; moving between machines means locking the vault and copying the file
  • Users who expect the server itself to run an LLM that extracts facts and decides what to remember; Compartment explicitly keeps no LLM inside and leaves that to the host model
  • Users who cannot keep a passphrase safe or who need a recovery path if it is lost, since Compartment never generates a password, seed or recovery phrase
  • Deployments that require network transports such as SSE or streamable-http; this server is stdio only and opens no ports
Required permissions
  • Sends diagram XML data to the hosted mcp.draw.io endpoint unless self-hosted
  • Loads draw.io viewer application code from app.diagrams.net / viewer.diagrams.net by default
  • No local filesystem or system access required when used as the hosted remote server
  • Read and write the vault file under the user's home directory, by default ~/.compartment/memory.vault, and its sibling settings file
  • Access the session directory holding the unlock credential (configurable with COMPARTMENT_SESSION_DIR), which also carries the shared embedding process's Unix socket
  • Optionally use the macOS keychain (compartment unlock --keychain is an explicit opt-in, and it survives reboots)
  • Write or merge an mcpServers entry into each MCP client's own configuration file, taking a byte-exact backup first
  • Install a PostToolUse hook for Claude Code that captures memory files the agent writes
  • Serve a read-only dashboard on 127.0.0.1 behind a one-time random URL token
Risks and side effects
  • Diagram content is sent to draw.io's hosted server when using the default mcp.draw.io endpoint
  • Outbound requests to app.diagrams.net/viewer.diagrams.net load viewer code by default unless built with VIEWER_PATH
  • Inline rendering depends on the host supporting the MCP Apps extension; otherwise only raw XML text is returned
  • A leaked passphrase means the encrypted content can be decrypted; Compartment generates no recovery phrase and cannot recover a lost passphrase
  • Enabling the memory_unlock tool places the passphrase in the model's context, which is why it is off by default
  • If a 2FA keyfile is lost, for example a USB stick, the vault cannot be opened even with the passphrase
  • `export --plaintext` writes the vault as unencrypted JSONL, so that file must be handled carefully
  • Memory content can come from untrusted sources; recall wraps memories with a notice that they are stored data and content can be marked quarantined, but the host agent must still treat memory as data to limit prompt-injection risk
  • The capture hook and client integration write into the user's own settings files, although the implementation backs up and merges rather than replacing
Supported clientsClaude.ai, Cursor, VS CodeClaude Desktop, Claude Code, Hermes Agent, OpenClaw, Cursor, VS Code, Codex, Gemini CLI, Cline, Roo Code, Zed, OpenCode, LM Studio, AnythingLLM, BoltAI, Goose, Kiro
Tools214